Score weighting in speaker verification systems

Download files
Access & Terms of Use
open access
Abstract
This paper presents a method for re-weighting the frame-based scores of a speaker recognition system according to the discrimination level of the best matched Gaussian mixture for that frame. This approach focuses on particular feature space regions that either have been modeled accurately or contain the phonemes which are inherently most discriminative.
Persistent link to this record
DOI
Additional Link
Author(s)
Ambikairajah, Eliathamby
Nosratighods, Mohaddeseh
Epps, Julien
Carey, Michael
Supervisor(s)
Creator(s)
Editor(s)
Translator(s)
Curator(s)
Designer(s)
Arranger(s)
Composer(s)
Recordist(s)
Conference Proceedings Editor(s)
Other Contributor(s)
Corporate/Industry Contributor(s)
Publication Year
2007
Resource Type
Conference Paper
Degree Type
UNSW Faculty
Files
download Score Weighting in Speaker Verification Systems.pdf 140.16 KB Adobe Portable Document Format
Related dataset(s)